When Does Model Collapse Occur in Structured Interactive Learning?

• URL: http://arxiv.org/abs/2605.20151v1
• Date: Tue, 19 May 2026 17:41:09 GMT
• Title: When Does Model Collapse Occur in Structured Interactive Learning?
• Abstract summary: We investigate the performance of generative models in an interactive learning environment with general interaction patterns.<n>We show that the occurrence of model collapse depends critically on the topology of the interaction graph.
• Score: 9.385946237424612
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The proliferation of generative artificial intelligence has given rise to an interactive learning environment, where model parameters are continuously updated using not only data generated by natural processes, but also synthetic outputs produced by other models. This paradigm introduces two major challenges: (1) training data are no longer drawn exclusively from the target population, undermining a core assumption of classical statistical learning, and (2) model training processes become inherently correlated, as models interact with one another through repeated exposure to each other's synthetic outputs in a potentially complex manner. Establishing reliable statistical inference in such structured interactive learning environments therefore remains an important open problem. In particular, there is growing concern about model collapse, a phenomenon in which the performance of generative models progressively degrades as they are trained on synthetic data produced by earlier model generations. Prior work on model collapse primarily focuses on a single model trained on its own output, failing to capture model performance in multi-model interactive settings. In this work, we fill this gap by investigating the performance of generative models in an interactive learning environment with general interaction patterns. In particular, we formalize model interactions using directed graphs and show that the occurrence of model collapse depends critically on the topology of the interaction graph. We further derive an explicit necessary and sufficient condition characterizing when model collapse occurs, and establish finite-sample results for linear regression and asymptotic guarantees for general M-estimators. We support our theoretical findings through extensive numerical experiments.

Related papers

• When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop [13.054822893327058]
  Self-consuming training can lead to model collapse, divergence, or bias amplification.<n>Recent work shows that incorporating human curation into the loop can steer a self-consuming model toward human-aligned behavior.<n>This paper studies self-consuming training in the multi-model regime.
  arXiv  Detail & Related papers  (2026-05-28T02:36:57Z)
• How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse [9.59833542807268]
  Model collapse occurs when new models are trained on synthetic data generated from previously trained models. We show that model collapse cannot be avoided when training solely on synthetic data. We estimate a maximal amount of synthetic data below which model collapse can eventually be avoided.
  arXiv  Detail & Related papers  (2024-04-07T22:15:13Z)
• Towards Theoretical Understandings of Self-Consuming Generative Models [56.84592466204185]
  This paper tackles the emerging challenge of training generative models within a self-consuming loop. We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models. We present results for kernel density estimation, delivering nuanced insights such as the impact of mixed data training on error propagation.
  arXiv  Detail & Related papers  (2024-02-19T02:08:09Z)
• From Identifiable Causal Representations to Controllable Counterfactual Generation: A Survey on Causal Generative Modeling [17.074858228123706]
  We focus on fundamental theory, methodology, drawbacks, datasets, and metrics. We cover applications of causal generative models in fairness, privacy, out-of-distribution generalization, precision medicine, and biological sciences.
  arXiv  Detail & Related papers  (2023-10-17T05:45:32Z)
• On the Stability of Iterative Retraining of Generative Models on their own Data [56.153542044045224]
  We study the impact of training generative models on mixed datasets. We first prove the stability of iterative training under the condition that the initial generative models approximate the data distribution well enough. We empirically validate our theory on both synthetic and natural images by iteratively training normalizing flows and state-of-the-art diffusion models.
  arXiv  Detail & Related papers  (2023-09-30T16:41:04Z)
• Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery [52.95935278819512]
  We conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDIALOG curated in our work. Inspired by causal discovery algorithms, we propose a novel model-agnostic method for training and inference of response generation model.
  arXiv  Detail & Related papers  (2023-03-02T06:33:48Z)
• De-Biasing Generative Models using Counterfactual Methods [0.0]
  We propose a new decoder based framework named the Causal Counterfactual Generative Model (CCGM) Our proposed method combines a causal latent space VAE model with specific modification to emphasize causal fidelity. We explore how better disentanglement of causal learning and encoding/decoding generates higher causal intervention quality.
  arXiv  Detail & Related papers  (2022-07-04T16:53:20Z)
• On the Generalization and Adaption Performance of Causal Models [99.64022680811281]
  Differentiable causal discovery has proposed to factorize the data generating process into a set of modules. We study the generalization and adaption performance of such modular neural causal models. Our analysis shows that the modular neural causal models outperform other models on both zero and few-shot adaptation in low data regimes.
  arXiv  Detail & Related papers  (2022-06-09T17:12:32Z)
• Closed-form Continuous-Depth Models [99.40335716948101]
  Continuous-depth neural models rely on advanced numerical differential equation solvers. We present a new family of models, termed Closed-form Continuous-depth (CfC) networks, that are simple to describe and at least one order of magnitude faster.
  arXiv  Detail & Related papers  (2021-06-25T22:08:51Z)
• Causal Inference with Deep Causal Graphs [0.0]
  Parametric causal modelling techniques rarely provide functionality for counterfactual estimation. Deep Causal Graphs is an abstract specification of the required functionality for a neural network to model causal distributions. We demonstrate its expressive power in modelling complex interactions and showcase applications to machine learning explainability and fairness.
  arXiv  Detail & Related papers  (2020-06-15T13:03:33Z)
• Hybrid modeling: Applications in real-time diagnosis [64.5040763067757]
  We outline a novel hybrid modeling approach that combines machine learning inspired models and physics-based models. We are using such models for real-time diagnosis applications.
  arXiv  Detail & Related papers  (2020-03-04T00:44:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.